Cross-lingual Transfer Efficiency via Intermediate Task Selection in XTREME Benchmarking

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tasks a

Research goal: How does the choice of English intermediate tasks (e.g., NLI, SQuAD, CoLA) influence zero-shot cross-lingual transfer efficiency (measured in inference latency and memory usage) when evaluated on the XTREME benchmark with a fixed computational budget?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.